• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.1
• /
• pp.21-31
• /
• 2002

This study applied each Neural Networks theory and Fuzzy Set theory to improve accuracy in remotely sensed images. Remotely sensed data have been used to map land cover. The accuracy is dependent on a range of factors related to the data set and methods used. Thus, the accuracy of maps derived from conventional supervised image classification techniques is a function of factors related to the training, allocation, and testing stages of the classification. Conventional image classification techniques assume that all the pixels within the image are pure. That is, that they represent an area of homogeneous cover of a single land-cover class. But, this assumption is often untenable with pixels of mixed land-cover composition abundant in an image. Mixed pixels are a major problem in land-cover mapping applications. For each pixel, the strengths of class membership derived in the classification may be related to its land-cover composition. Fuzzy classification techniques are the concept of a pixel having a degree of membership to all classes is fundamental to fuzzy-sets-based techniques. A major problem with the fuzzy-sets and probabilistic methods is that they are slow and computational demanding. For analyzing large data sets and rapid processing, alterative techniques are required. One particularly attractive approach is the use of artificial neural networks. These are non-parametric techniques which have been shown to generally be capable of classifying data as or more accurately than conventional classifiers. An artificial neural networks, once trained, may classify data extremely rapidly as the classification process may be reduced to the solution of a large number of extremely simple calculations which may be performed in parallel.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.29 no.2
• /
• pp.94-108
• /
• 1993

In order to investigate the relation between the environmental properties and catch fluctuation of set net fishing ground located in the coastal waters of Yeosu, oceanographic observation and catches on the grounds were carried out from Jan. to Dec. in 1990 and 1992. The results obtained are summarized as follows; 1) Because of the surveyed area is a costal shallow water, the fishing ground was influenced largely by atmospheric phenomena such as air temperature. precipitation. etc. and so showed large variations in temperature and salinity yearly. The inner water flowed out mainly between Yeosu ad Namhe-do, and then through Kumo-do between Dolsan-do and Kumo-do. On the other hand, off shore water was supplied into the fishing ground from the vicinity of Sori-do and Yokchi-do. thus the fishing ground was occupied usually by various sources of water. 2) The water mass in the fishing ground were divided into the inner water(29.0～30.6$\textperthousand$) and the mixed water(31,7～32.2$\textperthousand$) and off shore water(32.3～32.8$\textperthousand$) accourding to the distribution of salinity from T-S diagram plotted all salinity data observed in 1990 and 1992. In summer the inner and mixing water which was formed by river flowed southerly and spread south-easterly in the vicinity of Kumo-do. The off shore water which supplied from the vicinity of Sori-do and Yokchi-do and inner water formed the thermal front and halo front in summer. 3) The fishes caught by the set net were arranged in the order of catch amounts as follows: Spanish mackerel>Horse mackerel >Hair tail>Common mackerel> Sardine> Anchovy. The Catches of anchovy and sardine were high in April to May and those of hair tail and horse mackerel in July to September, but spanish mackerel were caught during the whole period of fishing. When inner water and mixing water appeared respectively and inner water and mixing water speared together in the set net fishing ground, the set net showed a high catch.

• Phonetics and Speech Sciences
• /
• v.9 no.1
• /
• pp.19-26
• /
• 2017

The main objective of this study is to investigate the influence of utterance internal pause in English speaking evaluation. To avoid possible confusion with other errors caused by segmental and prosodic inaccuracy, stem utterances with two different length obtained from a native speaker were manipulated to make a set of stimuli tokens through insertion of pauses whose length and position vary. After a total of 90 participants classified into three proficiency groups rated the stimuli, the scored data set was statistically analyzed in terms of the mixed effects model. It was confirmed that predictors such as pause length, pause position and utterance length significantly influence raters' evaluation scores. Especially, a dominating effect was found in such a way that raters gradually deducted scores in accordance with the increase of pause duration. In another experiment, a tree-based statistical learning technique was utilized to check which of the significant predictors played a more influential role than others. The findings in this paper are expected to be practically informative for both the test takers who are preparing for an English speaking test and the raters who desire to develop more objective rubric of speaking evaluation.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.5
• /
• pp.15-24
• /
• 2020

We present a supervised learning method that estimates the simulation parameters required to simulate the fabric from the static drape shape of a given fabric sample. The static drape shape was inspired by Cusick's drape, which is used in the apparel industry to classify fabrics according to their mechanical properties. The input vector of the training model consists of the feature vector extracted from the static drape and the density value of a fabric specimen. The output vector consists of six simulation parameters that have a significant influence on deriving the corresponding drape result. To generate a plausible and unbiased training data set, we first collect simulation parameters for 400 knit fabrics and generate a Gaussian Mixed Model (GMM) generation model from them. Next, a large number of simulation parameters are randomly sampled from the GMM model, and cloth simulation is performed for each sampled simulation parameter to create a virtual static drape. The generated training data is fitted with a log-linear regression model. To evaluate our method, we check the accuracy of the training results with a test data set and compare the visual similarity of the simulated drapes.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.5
• /
• pp.259-266
• /
• 2014

In this paper, we propose a novel technique for noise robust automatic speech recognition (ASR). The development of ASR techniques has made it possible to recognize isolated words with a near perfect word recognition rate. However, in a highly noisy environment, a distinct mismatch between the trained speech and the test data results in a significantly degraded word recognition rate (WRA). Unlike conventional ASR systems employing Mel-frequency cepstral coefficients (MFCCs) and a hidden Markov model (HMM), this study employ histogram of oriented gradient (HOG) features and a Support Vector Machine (SVM) to ASR tasks to overcome this problem. Our proposed ASR system is less vulnerable to external interference noise, and achieves a higher WRA compared to a conventional ASR system equipped with MFCCs and an HMM. The performance of our proposed ASR system was evaluated using a phonetically balanced word (PBW) set mixed with artificially added noise.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2007.04a
• /
• pp.67-70
• /
• 2007

As construction industry is requiring competitive power and technique in national construction market with rapid fluctuation of construction environment and development, requirements upgrading performance in construction materials are increasing. But, national lightweight aggregate and lightweight concrete's inappropriateness when produced are also increasing. And there are not international standard of aggregates in using these construction materials because standards and characteristics of aggregate in each countries are different. Therefore, in this study, lightweight aggregate acquired due to wide range of use is tested and mixed for concrete to gain practicality and set the authorized manual in international. Also, basic data will be proposed to set a standard for concrete by analyzing lightweight aggregate characteristics. When lightweight aggregate absorptivity is high, concrete shows low strength and when it's density is low, concrete shows low weight of unit volume. Furthermore, compressive strength of lightweight aggregate is steep in first and longtime material age is tendency to cause low strength increasing rate.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.269-276
• /
• 2011

This paper considers the rail crane scheduling problem with minimizing the sum of the range of order completion time and make-span of rail crane simultaneously. The range of order completion time implies the difference between the maximum of completion time and minimum of start time. Make-span refers to the time when all the tasks are completed. At a rail terminal, logistics companies wish to concentrate on their task of loading and unloading container on/from rail freight train at a time in order to increase the efficiency of their equipment such as reach stacker. In other words, they want to reduce the range of their order completion time. As a part of efforts to meet the needs, the crane schedule is rearranged based on worker's experience. We formulate the problem as a mixed integer program. To validate the effectiveness of the model, computational experiments were conducted using a set of data randomly generated.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.48 no.2
• /
• pp.221-228
• /
• 2021

The aim of this study was to evaluate the use of easily accessible machine learning application to identify mesiodens, and to compare the ability to identify mesiodens between trained model and human. A total of 1604 panoramic images (805 images with mesiodens, 799 images without mesiodens) of patients aged 5 - 7 years were used for this study. The model used for machine learning was Google's teachable machine. Data set 1 was used to train model and to verify the model. Data set 2 was used to compare the ability between the learning model and human group. As a result of data set 1, the average accuracy of the model was 0.82. After testing data set 2, the accuracy of the model was 0.78. From the resident group and the student group, the accuracy was 0.82, 0.69. This study developed a model for identifying mesiodens using panoramic radiographs of children in primary and early mixed dentition. The classification accuracy of the model was lower than that of the resident group. However, the classification accuracy (0.78) was higher than that of dental students (0.69), so it could be used to assist the diagnosis of mesiodens for non-expert students or general dentists.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1733-1739
• /
• 2006

This paper is concerned with multi-objective vehicle routing problem(VRP), in which objective of this problem is to minimize the total operating time of vehicles and the total tardiness of customers. A mixed integer programming formulation and a heuristic for practical use are suggested. The heuristic is based on the route-perturbation and route-improvement method(RPRI). Performances are compared with other heuristic appeared in the previous literature using the modified bench-mark data set. It is shown that the suggested heuristic give good solution within a short computation time by computational experiment.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.71-89
• /
• 2003

Although many studies demonstrate that one technique outperforms the others for a given data set, there is often no way to tell a priori which of these techniques will be most effective in the classification problems. Alternatively, it has been suggested that a better approach to classification problem might be to integrate several different forecasting techniques. This study proposes the linearly combining methodology of different classification techniques. The methodology is developed to find the optimal combining weight and compute the weighted-average of different techniques' outputs. The proposed methodology is represented as the form of mixed integer programming. The objective function of proposed combining methodology is to minimize total misclassification cost which is the weighted-sum of two types of misclassification. To simplify the problem solving process, cutoff value is fixed and threshold function is removed. The form of mixed integer programming is solved with the branch and bound methods. The result showed that proposed methodology classified more accurately than any of techniques individually did. It is confirmed that Proposed methodology Predicts significantly better than individual techniques and the other combining methods.